INDEX

Explanations

verbs related to achievement or accomplishment

oai_token-act-pair · gpt-3.5-turbo

verbs and auxiliary verbs indicating actions or states of being in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

zo

-0.71

Ago

-0.70

Lun

-0.69

 Awakens

-0.67

Sol

-0.67

 Kron

-0.64

Aer

-0.63

 Shal

-0.61

 bond

-0.61

 Ital

-0.61

POSITIVE LOGITS

 somehow

0.89

 indistinguishable

0.82

Ļ½

0.79

 disproportionately

0.78

entimes

0.76

 inex

0.74

ŃĶ

0.73

çĶ°

0.71

 inevitably

0.71

 outwe

0.70

Activations Density 0.928%

verbs related to achievement or accomplishment

verbs and auxiliary verbs indicating actions or states of being in various contexts

No Comments

No Known Activations